// Applied Research Engineer, Agentic Code Generation //

Tabnine acquired.

Tabnine has been acquired by Tricentis, the global leader in agentic quality engineering.

Read more

Log in Get a demo

< View all positions

//Applied Research Engineer, Agentic Code Generation//

Tel Aviv/Full-time

A Bit About Us:

Tabnine is redefining how software gets built. Trusted by over 1M+ developers, we build AI-first developer experiences powered by state-of-the-art coding agents and code reasoning models. With support for 30+ programming languages and 15+ IDEs, our platform is pushing the limits of LLM-based software engineering - enabling teams to design, write, review, and ship code faster than ever. We’re committed to advancing code-native AI models, multi-agent systems, agent orchestration frameworks, memory, and autonomous dev tooling to empower developers at every step of the software lifecycle.

We’re growing fast, and our team is passionate about pushing AI engineering to new heights - solving complex problems in LLM training, inference optimization, reasoning, and agent orchestration at scale.

About The Role:

As an Applied Research Engineer you’ll work on cutting-edge

code-focused LLMs and AI agent systems

that power Tabnine’s next-generation developer platform. You’ll be at the center of research, model training, and productionization of intelligent systems that understand software deeply, collaborate with developers, and help automate engineering workflows end-to-end. Your work will immediately impact millions of engineers worldwide.

Responsibilities:

• Push LLM Innovation: Research, design, and fine-tune domain-specific LLMs for code generation, refactoring, debugging, and multi-turn reasoning.
• Agent-Oriented Development: Build multi-agent coding systems that integrate retrieval-augmented generation (RAG), code execution, testing, and tool use to create autonomous, context-aware coding workflows.
• Production-Grade AI: Own the training-to-inference pipeline for large code models—optimize inference with quantization, distillation, and caching techniques.
• Rapid Experimentation: Prototype and validate ideas quickly; leverage reinforcement learning, human feedback, and synthetic data generation to push accuracy and reasoning.
• Cross-Functional Collaboration: Partner with product, engineering, and design teams to ship AI-powered features that help developers focus on high-impact work.
• Scale the Platform: Contribute to distributed training, scalable serving systems, and GPU/TPU-efficient architectures for ultra-low-latency developer tools.
  
  

Requirements:

• 2+ years of hands-on experience designing, training, and deploying machine-learning models
• M.Sc. or higher in Computer Science / Mathematics / Statistics or equivalent from a university, or B.Sc. with strong hands-on ML experience
• Practical experience with Natural Language Processing (NLP) and LLMs
• Experience with data acquisition, data cleaning, and data pipelines
• A passion for building products and helping people, both customers and colleagues
• All-around team player, fast, self-learning individual
  
  

Nice To Have:

• 3+ years of development experience with a passion for excellence
• Experience building AI coding assistants, code reasoning models, or dev-focused LLM agents.
• Familiarity with RAG, function-calling, and tool-using LLMs.
• Knowledge of model optimizations (quantization, distillation, LoRA, pruning).
• Startup or product-driven ML experience, especially in high-scale, latency-sensitive environments.
• Contributions to open-source AI or developer tools.
  
  

Share this job

// We work. And play. //

We love our work, we love collaborating with do-good people that love their work as well. But, we never forget to have fun. Join us.

Apply now View all positions

//Applied Research Engineer, Agentic Code Generation//

Tel Aviv/Full-time

Please complete the form below to apply

• Tabnine
• About
• Careers
• Contact Us
• Partners
• Product
• Plans & Pricing
• Supported IDEs
• Documentation
• Resources
• Code Privacy
• Privacy Policy
• Terms of Use
• Trust Center
• Tabnine Cookie Policy
• Knowledge Center
• AI code generation
• Code refactoring
• Code debugging
• Code documentation
• Unit testing
  

//

Tabnine is the AI coding platform you can deploy anywhere, cloud, on-prem, or air-gapped, while accelerating software development and keeping your code private, secure, and compliant.

//

Introducing the Tabnine Enterprise Context Engine

• Products
• Tabnine AI Coding Platform – AI chat, completions, and agentic workflows across IDE and CLI
• Tabnine Context Engine – Organizational intelligence that gives agents system-level understanding
• How it works
• The Tabnine Agentic Platform – Org-Native AI Agents that plan & execute workflows with enterprise context
• Industry-leading AI code assistant – Ship better software faster with the original AI developer tool
• Run AI workflows in the CLI – Bring AI-powered coding, automation, and agents into your terminal.
• Al chat that supports the entire SDLC – Improve your code with AI-powered chat at every stage of development
• Total code privacy & zero data retention – Secure the confidentiality and integrity of your codebase
• Complete protection from IP issues – Ensure copyright compliance with code scanning and license-compliant models
• Pricing
• AI Coding Platform – AI chat completions and agentic workflows for software development
• Enterprise Context Engine – Organizational intelligence that gives agents system-level understanding
• Docs
• Resources
• // Featured Article //
  

Continue

//

Featured Product News

//

Introducing the Tabnine CLI

InfoWorld’s 2025 Technology of the Year

Introducing Provenance and Attribution

More

//

Featured Thought Leadership

//

Before You Scale AI for Software Dev, Fix How You Measure…

Vibe coding your way into a tsunami of technical debt

Your AI Doesn’t Need More Training—It Needs Context.

More

• Guides and Reports
• Videos
• Blog
• Product Comparisons
• Al technology guide
• Machine learning guide
  
  

Tel Aviv/Full-time

Responsibilities:

• Push LLM Innovation: Research, design, and fine-tune domain-specific LLMs for code generation, refactoring, debugging, and multi-turn reasoning.
• Agent-Oriented Development: Build multi-agent coding systems that integrate retrieval-augmented generation (RAG), code execution, testing, and tool use to create autonomous, context-aware coding workflows.
• Production-Grade AI: Own the training-to-inference pipeline for large code models—optimize inference with quantization, distillation, and caching techniques.
• Rapid Experimentation: Prototype and validate ideas quickly; leverage reinforcement learning, human feedback, and synthetic data generation to push accuracy and reasoning.
• Cross-Functional Collaboration: Partner with product, engineering, and design teams to ship AI-powered features that help developers focus on high-impact work.
• Scale the Platform: Contribute to distributed training, scalable serving systems, and GPU/TPU-efficient architectures for ultra-low-latency developer tools.
  
  

Requirements:

• 2+ years of hands-on experience designing, training, and deploying machine-learning models
• M.Sc. or higher in Computer Science / Mathematics / Statistics or equivalent from a university, or B.Sc. with strong hands-on ML experience
• Practical experience with Natural Language Processing (NLP) and LLMs
• Experience with data acquisition, data cleaning, and data pipelines
• A passion for building products and helping people, both customers and colleagues
• All-around team player, fast, self-learning individual
  
  

Nice To Have:

• 3+ years of development experience with a passion for excellence
• Experience building AI coding assistants, code reasoning models, or dev-focused LLM agents.
• Familiarity with RAG, function-calling, and tool-using LLMs.
• Knowledge of model optimizations (quantization, distillation, LoRA, pruning).
• Startup or product-driven ML experience, especially in high-scale, latency-sensitive environments.
• Contributions to open-source AI or developer tools.
  
  

We love our work, we love collaborating with do-good people that love their work as well. But, we never forget to have fun. Join us.

//Applied Research Engineer, Agentic Code Generation//

Tel Aviv/Full-time

Please complete the form below to apply

Tel Aviv/Full-time

• Tabnine
• About
• Careers
• Contact Us
• Partners
• Product
• Plans & Pricing
• Supported IDEs
• Documentation
• Resources
• Code Privacy
• Privacy Policy
• Terms of Use
• Trust Center
• Tabnine Cookie Policy
• Knowledge Center
• AI code generation
• Code refactoring
• Code debugging
• Code documentation
• Unit testing
  

//

Tabnine is the AI coding platform you can deploy anywhere, cloud, on-prem, or air-gapped, while accelerating software development and keeping your code private, secure, and compliant.

//

//

Featured Article

//

Introducing the Tabnine Enterprise Context Engine

Continue

//

Featured Product News

//

Introducing the Tabnine CLI

InfoWorld’s 2025 Technology of the Year

Introducing Provenance and Attribution

More

//

Featured Thought Leadership

//

Before You Scale AI for Software Dev, Fix How You Measure…

Vibe coding your way into a tsunami of technical debt

Your AI Doesn’t Need More Training—It Needs Context.

More