Generative AI Engineer

About Codewalla

At Codewalla, we don’t just experiment with AI—we ship AI-native products that scale.

Born in New York and growing across India, we partner with ambitious startups to build the next generation of AI-accelerated software. Our work is fast-paced, deeply technical, and relentlessly user-focused. From LLM-powered copilots to vector search-backed dashboards, we bring AI from concept to production—without losing sight of cost, latency, or reliability.

We don’t just believe in smart code. We believe in delivering smart experiences.

About the Role

6–8 years of engineering experience

Your mission: translate raw model capability into lean, reliable, and user-ready features. You’ll work on Model Context Protocol (MCP) servers, build agentic clients, architect RAG pipelines, and automate LLM evaluations to ensure every release delivers measurable value.

If you thrive on rapid iteration, prompt experimentation, and seeing your code make it into users’ hands—we’d love to hear from you.

What You’ll Work On

• Build MCP servers and agentic clients that handle user intent parsing, tool orchestration, and structured response generation
• Architect efficient RAG pipelines with chunk decay, latency budgeting, and cost-aware vector search
• Automate evaluation pipelines that test LLM outputs for relevance, accuracy, and coherence
• Work closely with DevOps to codify and deploy infrastructure using CDK or Terraform
• Set up observability dashboards for prompt performance, latency, and failure traceability
• Continuously refine prompts, embeddings, and model behavior based on user feedback and regression tests

What Makes You a Great Fit

• 6–8 years of full-stack or backend development experience, with at least 1 year building AI-powered or LLM-based applications
• AI-native mindset: test fast, trace deeply, pause to reframe when needed
• Strong Python and TypeScript skills
• Experience with either AWS or GCP stacks, such as:
• AWS: Lambda, Bedrock, DynamoDB, OpenSearch Vector Search
• GCP: Cloud Functions, Vertex AI, Firestore, BigQuery, Vector Search
• Familiarity with LangChain, Bedrock SDK, and vector database schema design
• Understanding of prompt design, embeddings, and agentic workflows
• CI/CD fluency—GitHub Actions, containerized deployment, test-first habits
• Experience with LLM evaluation tools like Promptfoo, LangSmith, or Guardrails
• Bonus: Experience with MLflow, LaunchDarkly, Inferentia/GPU tuning

Tools & Tech We Work With

• Languages: Python, TypeScript
• Frameworks: LangChain, FastAPI, Next.js
• Cloud: AWS (Bedrock, Lambda, DynamoDB, OpenSearch Vector Search) or GCP (Vertex AI, Cloud Functions, Firestore, BigQuery, Vector Search)
• Dev Tools: GitHub Copilot, Cursor
• Evaluation & Safety: Promptfoo, LangSmith, Guardrails
• DevOps: GitHub Actions, CDK or Terraform, Docker, Prometheus, Grafana

Why Join Codewalla?

• Work at the forefront of AI-native product development
• Ship features that go from prototype to production, not just to playgrounds
• Collaborate with world-class teams building real-world tools for global users
• Influence everything—from prompt strategy to model integration and deployment pipelines
• Your code will shape actual user experience—not just a research slide deck

Inclusion Matters

We’re an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all team members.

Ready to build the future with LLMs—without waiting for the future to catch up?

Apply now and let’s build together.