Sr Python Backend Engineer - AI/LLM

Job Summary

We are looking for a hands-on Senior Python Backend Engineer to help build and scale MyKarb, Nirantaras AI-guided Life Cycle Assessment and Product Carbon Footprint platform. You will develop backend services, data pipelines, and applied AI workflows that guide users through complex sustainability assessments and connect product data with verified lifecycle datasets.

You will work with technology leadership, engineers, QA, product stakeholders and LCA specialists in a fast-moving product team. The role requires strong software-engineering judgement, comfort with ambiguous business requirements and ownership from technical design through production support.

This position combines production Python backend engineering with applied AI. The priority is building reliable APIs, rule-driven workflows, background-processing pipelines and grounded LLM capabilities.

Responsibilities

• Backend services and APIs. Design, build and maintain secure, scalable FastAPI services and REST APIs supporting MyKarbs LCA, PCF and EPD workflows.
• Applied AI and RAG. Develop LLM and prompt workflows using structured outputs, retrieval, grounding, guardrails, evaluation and human-review paths where required.
• Rules and auditability. Implement deterministic validations and rule-driven decision logic for standards, PCR/EPD requirements and other compliance-sensitive workflows, with traceable evidence and audit trails.
• Background processing. Build reliable Celery-based jobs and distributed workflows with retries, idempotency, monitoring and failure recovery.
• Data and performance. Design data models, optimise database queries, caching, latency, token use and computation cost across production workloads.
• Engineering quality. Write automated tests, review code, document technical decisions and contribute to CI/CD, observability, security and production reliability.
• Cross-functional delivery. Translate BRDs and inputs from domain specialists into maintainable technical solutions and deliver production-ready features in two-week sprints.

Requirements

• 5+ years of professional software engineering experience with strong hands-on Python backend development.
• Production experience with FastAPI and modern Python practices, including typing, asynchronous programming, Pydantic and maintainable service architecture.
• Experience designing and documenting REST APIs, authentication, validation, error handling and API versioning.
• Strong database skills with PostgreSQL or another relational database, plus experience with SQLAlchemy or a comparable ORM.
• Experience with Celery and Redis, RabbitMQ or another task queue/message broker, including retries and failure handling.
• Hands-on experience building LLM-enabled applications using prompt engineering, structured outputs, embeddings, RAG, semantic search or vector databases.
• Experience with automated testing using pytest, including unit and integration tests for APIs and data-processing workflows.
• Experience with Docker, Git, code reviews and CI/CD, plus practical exposure to deploying and operating cloud-based services.
• Strong debugging and problem-solving ability across application code, databases, distributed jobs and external integrations.
• Clear communication and the ability to collaborate with engineers, QA, product stakeholders and non-technical domain experts.
• Genuine interest in sustainability, climate technology or ESG and willingness to learn the fundamentals of LCA and carbon accounting.

Preferred qualifications

• Experience with LangChain, LlamaIndex or a comparable LLM orchestration framework.
• Experience designing evaluation frameworks for retrieval relevance, LLM output quality, hallucination control or human-in-the-loop review.
• Experience with vector databases, search infrastructure or large catalogue-matching and ranking problems.
• Experience with Pandas, NumPy or scientific/data-processing workloads.
• Experience with application monitoring, structured logging, Sentry or similar observability tools.
• Knowledge of microservices, distributed systems, infrastructure-as-code or Kubernetes where relevant to production deployment.

Location: Pune

Job Type: Full-time, Hybrid

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.