Lead development of LLM-powered applications and agentic workflows: implement RAG pipelines, vector DB integrations, prompt orchestration, AI agents, and REST microservices. Optimize inference, deployment (containers/CI-CD/cloud), and evaluate model accuracy/hallucination. Debug performance issues and document designs.
Responsibilities
GenAI Application Development
- Develop LLM-powered applications using Python-based frameworks.
- Implement RAG pipelines and vector database integrations.
- Build prompt orchestration workflows and response optimization logic.
Agentic Workflow Implementation
- Develop AI agents with tool integration capabilities.
- Implement reasoning loops, memory modules, and execution controls.
- Integrate AI agents into backend systems and APIs.
Deployment & Optimization
- Build REST APIs and microservices for AI applications.
- Optimize inference performance, latency, and cost.
- Support CI/CD pipelines and cloud deployments.
Testing & Quality
- Implement evaluation metrics for hallucination control and accuracy.
- Debug and resolve performance bottlenecks.
- Document code, workflows, and solution design.
Experience and Competency Requirements
- 4–8 years of software development experience.
- 2+ years working with AI/ML or GenAI applications.
- Strong proficiency in Python.
- Experience with LLM APIs, embeddings, and vector databases.
- Exposure to cloud-based deployments and containerization.
- Strong analytical and debugging capabilities.
- Should have decent to good experience in data handling and analytics with python
Skills
GenAI & LLM Frameworks (Mandatory)
- OpenAI APIs / Azure OpenAI
- LangChain / LangGraph / LlamaIndex
- Transformers (Hugging Face)
- Prompt engineering and evaluation frameworks
Agentic Systems & Orchestration
- Multi-agent design patterns (MCP, A2A, ReAct etc)
- Tool integrations and API orchestration
- Memory frameworks and contextual reasoning
- Guardrails, observability, and monitoring
Data & Infrastructure
- Vector databases (Pinecone, FAISS, Weaviate or equivalent)
- Python, FastAPI, REST services
- Docker, Kubernetes
- Cloud platforms (AWS, Azure, GCP)
Data Handling & Analytics Skills
- Data preprocessing and ETL for structured and unstructured data
- Data manipulation using Pandas, NumPy, and SQL
- Exploratory data analysis (EDA) and statistical analysis
- Data visualization (Matplotlib, Seaborn, Plotly, Tableau, Power BI)
Responsibilities
GenAI Application Development
- Develop LLM-powered applications using Python-based frameworks.
- Implement RAG pipelines and vector database integrations.
- Build prompt orchestration workflows and response optimization logic.
Agentic Workflow Implementation
- Develop AI agents with tool integration capabilities.
- Implement reasoning loops, memory modules, and execution controls.
- Integrate AI agents into backend systems and APIs.
Deployment & Optimization
- Build REST APIs and microservices for AI applications.
- Optimize inference performance, latency, and cost.
- Support CI/CD pipelines and cloud deployments.
Testing & Quality
- Implement evaluation metrics for hallucination control and accuracy.
- Debug and resolve performance bottlenecks.
- Document code, workflows, and solution design.
Experience and Competency Requirements
- 4–8 years of software development experience.
- 2+ years working with AI/ML or GenAI applications.
- Strong proficiency in Python.
- Experience with LLM APIs, embeddings, and vector databases.
- Exposure to cloud-based deployments and containerization.
- Strong analytical and debugging capabilities.
- Should have decent to good experience in data handling and analytics with python
Skills
GenAI & LLM Frameworks (Mandatory)
- OpenAI APIs / Azure OpenAI
- LangChain / LangGraph / LlamaIndex
- Transformers (Hugging Face)
- Prompt engineering and evaluation frameworks
Agentic Systems & Orchestration
- Multi-agent design patterns (MCP, A2A, ReAct etc)
- Tool integrations and API orchestration
- Memory frameworks and contextual reasoning
- Guardrails, observability, and monitoring
Data & Infrastructure
- Vector databases (Pinecone, FAISS, Weaviate or equivalent)
- Python, FastAPI, REST services
- Docker, Kubernetes
- Cloud platforms (AWS, Azure, GCP)
Data Handling & Analytics Skills
- Data preprocessing and ETL for structured and unstructured data
- Data manipulation using Pandas, NumPy, and SQL
- Exploratory data analysis (EDA) and statistical analysis
- Data visualization (Matplotlib, Seaborn, Plotly, Tableau, Power BI)
Minimum Qualification
Bachelor’s degree required
M.Tech/ MS in Computer Science, AI, or related field preferred; Required Experience: 4-6 years
What you need to know about the Pune Tech Scene
Once a far-out concept, AI is now a tangible force reshaping industries and economies worldwide. While its adoption will automate some roles, AI has created more jobs than it has displaced, with an expected 97 million new roles to be created in the coming years. This is especially true in cities like Pune, which is emerging as a hub for companies eager to leverage this technology to develop solutions that simplify and improve lives in sectors such as education, healthcare, finance, e-commerce and more.
