Role Overview :

We are seeking a highly motivated Agentic AI Developer to design, develop, and deploy intelligent AI systems that leverage Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and multi-agent architectures.

The ideal candidate will have hands-on experience building production-grade AI applications, developing agentic workflows, and integrating AI solutions into enterprise environments.

This role requires a blend of software engineering, machine learning, and AI application development expertise, with a strong focus on building scalable, reliable, and business-impacting AI solutions.

Key Responsibilities :

- Design and develop AI agents and multi-agent workflows using modern orchestration frameworks such as LangChain, LangGraph, and similar agentic frameworks.

- Build autonomous and semi-autonomous AI systems capable of planning, reasoning, tool usage, and workflow orchestration.

- Develop AI solutions that balance automation with human-in-the-loop review where required.

- Design and implement end-to-end Retrieval-Augmented Generation (RAG) pipelines, including :

1. Document ingestion

2. Data preprocessing and chunking

3. Embedding generation

4. Vector database integration

5. Retrieval and reranking

6. Grounded response generation

- Optimize prompt engineering, retrieval strategies, and response quality to improve system performance and reliability.

- Integrate LLMs and foundation models into enterprise applications and business workflows.

- Translate business requirements into scalable AI architectures and technical solutions.

- Define workflow logic, agent interactions, automation boundaries, and human review checkpoints.

- Collaborate with business stakeholders, product teams, and engineering teams to identify high-impact AI use cases.

- Develop evaluation frameworks and testing methodologies to measure retrieval quality, response accuracy, relevance, and system performance.

- Build lightweight evaluation harnesses and benchmarking mechanisms for AI applications.

- Monitor production systems for model drift, degradation, hallucinations, and performance issues.

- Continuously improve AI systems through experimentation and iterative optimization.

- Apply MLOps best practices including :

1. Experiment tracking

2. Model versioning

3. Monitoring and observability

4. Drift detection

5. CI/CD for AI applications

- Containerize and deploy AI services using Docker and cloud-native deployment practices.

- Support scalable deployment and maintenance of AI applications in production environments.

- Stay updated with emerging trends in Generative AI, Agentic AI, LLMs, RAG architectures, and AI engineering practices.

- Contribute to internal AI accelerators, reusable frameworks, and best practices.

- Participate in architecture discussions, code reviews, and technical knowledge-sharing initiatives.

Required Qualifications :

- Bachelor's degree in Computer Science, Engineering, Data Science, Statistics, Mathematics, or a related field.

- 2-7 years of experience in Software Development, Machine Learning, AI Engineering, Data Science, or AI Solution Development.

- Strong programming skills in Python and working knowledge of SQL.

- Hands-on experience building and deploying AI/ML applications in production environments.

- Experience with :

1. Large Language Models (LLMs)

2. Retrieval-Augmented Generation (RAG)

3. LangChain and/or LangGraph

4. Vector Databases

5. Prompt Engineering

- Familiarity with Docker and containerized deployment workflows.

- Strong analytical, problem-solving, and communication skills.

Preferred Skills :

- Experience with cloud platforms such as AWS, Azure, or GCP.

- Knowledge of MLOps tools and frameworks.

- Experience with APIs, microservices, and distributed systems.

- Familiarity with observability and monitoring tools.

- Exposure to open-source LLMs and model serving frameworks.

- Experience integrating AI solutions with enterprise applications and business processes.