LLM Full Stack Engineer

Project Role :LLM Full Stack Engineer


Project Role Description :Develop and integrate applications with Large Language Models (LLMs) and other enterprise services. Leverage front-end and server-side technologies to develop APIs, implement DevOps practices, and optimize Artificial Intelligence (AI) applications.
Must have skills :Large Language Models (LLMs), React.js, Prompt Engineering, Generative AI

Good to have skills :NA
Minimum 5 year(s) of experience is required

Educational Qualification :15 years full time education

Summary:
As an LLM Full Stack Engineer, a typical day involves designing and building applications that seamlessly integrate with Large Language Models and various enterprise services. The role requires balancing front-end and back-end development tasks, creating robust application programming interfaces, and ensuring smooth deployment through DevOps methodologies. The engineer collaborates with cross-functional teams to enhance the performance and scalability of artificial intelligence solutions, continuously refining systems to meet evolving business needs and technological advancements.

Roles Responsibilities:
- Expected to be an SME, collaborate and manage the team to perform.
- Responsible for team decisions.
- Engage with multiple teams and contribute on key decisions.
- Provide solutions to problems for their immediate team and across multiple teams.
- Lead the design and implementation of scalable AI-driven applications that leverage Large Language Models.
- Facilitate knowledge sharing and mentorship within the team to foster professional growth.
- Coordinate with stakeholders to align technical solutions with business objectives.

Professional Technical Skills:
- Software engineering 6+ years with Python building production services.
- Proven delivery of LLM/GenAI systems:prompts, tool/function calling, RAG pipelines, and multi-agent orchestration.
- Backend expertise:FastAPI/Django, async programming, testing (pytest), and performance profiling.
- Frontend proficiency:React/Next.js, TypeScript, state management (Redux/RTK/Zustand), and component testing (Jest/RTL/Cypress).
- Retrieval:embeddings and indexing, vector DBs, query/rerank strategies, and data governance basics.
- DevOps:CI/CD, Docker, basic Kubernetes (deployments, secrets, config), monitoring (App Insights/Prometheus/Grafana).
- Strong API design, security (OAuth2/OIDC, JWT, RBAC), and observability skills.
- Azure AI/OpenAI experience Azure AI Studio, Cognitive Search, Key Vault, Purview, Event Hubs.
- Experience with LangGraph, AutoGen, CrewAI, Semantic Kernel planners/memory/skills.
- Knowledge of document pipelines (pdf/images/OCR), rerankers, and safety tooling.
- Experience with feature stores / ML inference, or streaming (Kafka/Event Hubs).
- Performance/load testing (Locust/Gatling/JMeter) and cost governance for LLM workloads.

Must To Have Skills:

- Proficiency in Large Language Models (LLMs), Generative AI, Prompt Engineering, React.js.
- Strong experience in developing and integrating APIs for AI applications.
- Familiarity with front-end frameworks and server-side technologies to build full stack solutions.
- Understanding of DevOps practices to automate deployment and monitoring of AI systems.
- Ability to optimize AI models and applications for performance and scalability.
- Experience working with cloud platforms and containerization technologies.
- The candidate should have minimum 6 years of experience in Large Language Models (LLMs).
- This position is based at our Pune office.
- A 15 years full time education is required.




Qualification
15 years full time education