Job Summary
Key Responsibilities
1. To develop & deliver codes for the project/ work assigned by following established standards of quality and delivery SLA
2. To maintain the existing project by resolving/troubleshooting/debugging issues occurring in the existing project/application.
3. To understand client requirements and accordingly develop code to create required features.
4. Documentation of work.
Skill Requirements
- Hands-on or academic/project experience with:
- Large Language Models (LLMs) – OpenAI, Anthropic, AWS Bedrock, or open-source models
- RAG (Retrieval-Augmented Generation) concepts and vector databases (e.g., FAISS, Pinecone, Chroma)
- Exposure to agent frameworks such as LangChain, CrewAI, AutoGen, or similar
- Basic understanding of:
- Prompt engineering techniques and prompt optimisation
- Embeddings and semantic search concepts
- Context handling and token usage strategies
- Experience (projects/internships) in building:
- Simple AI workflows or multi-step pipelines
- Rule-based or LLM-driven chatbots or agents
Other Requirements
- Python programming with the ability to build modular and maintainable backend components
- Basic understanding of RESTful APIs and integration of backend services
- Familiarity with microservices architecture and scalable system design concepts
- Good knowledge of data structures, algorithms, and problem-solving techniques
- Exposure to databases (SQL/NoSQL) and version control systems (Git)
- Understanding of software development lifecycle (SDLC) and coding best practices
- Exposure to cloud platforms (AWS/Azure/GCP)
- Knowledge of Docker or containerisation basics
- Familiarity with API deployment and testing tools (Postman, FastAPI, Flask)
- Understanding of AI ethics, data privacy, and responsible AI practices
Soft Skills
- Strong analytical and learning mindset
- Ability to work in a fast-paced, collaborative environment
- Good communication skills for technical discussions