Position: Python Engineer Agentic AI

Experience: 3- 8 Years

Location: Bangalore / Hyderabad

Work Mode: 5 Days Work From Office (Initially)

Notice Period: 0 to 15 days

Job type: Contract

Job Description:

- Bachelors or Masters degree in Computer Science, Engineering, or related field.

- 3+ years of professional Python development experience.

- 3+ years of proven experience as a Python Developer with a focus on AI/ML (such as TensorFlow, PyTorch, or Keras or equivalent).

- 2+ Exposure to Generative AI and Agentic AI frameworks and platforms (e.g., OpenAI, LangChain LlamaIndex, LangGraph).

- 2+ Understanding of LLMs, prompt engineering, and RAG architectures.

- 2+ Experience with cloud platforms (AWS, GCP, Azure) and containerization (Docker, Kubernetes).

- 3+ Familiarity with RESTful APIs, microservices, and event-driven architectures.

- 3+ Excellent problem-solving skills and ability to work in a fast-paced, collaborative environment.

- 3+ Exposure to MLOps tools and CI/CD pipelines.

Role Overview:

As a Python Engineer specializing in Agentic AI, you will be at the forefront of building autonomous, intelligent systems that redefine how our business interacts with complex data. Your day-to-day involves architecting sophisticated AI agents, designing robust workflows using LangGraph, and integrating Large Language Models into production-grade applications.

You will collaborate closely with cross-functional product teams, data scientists, and stakeholders to translate ambiguous business challenges into scalable AI solutions. By bridging the gap between experimental research and real-world deployment, your work will directly enhance user experiences and drive operational efficiency, positioning our products as industry leaders in the generative AI space.

Key Responsibilities:

- Engineer and deploy autonomous AI agents that automate complex decision-making processes to streamline internal workflows and improve customer outcomes.

- Design and maintain scalable AI pipelines using LangChain and LangGraph to ensure reliable, multi-step reasoning capabilities within our applications.

- Optimize Retrieval-Augmented Generation (RAG) architectures and VectorDB implementations to provide our models with accurate, context-aware data retrieval.

- Develop high-performance backend services using FastAPI to serve AI-driven features, ensuring low latency and seamless integration with existing infrastructure.

- Conduct rigorous prompt engineering and model fine-tuning experiments to improve the accuracy, safety, and relevance of LLM outputs for end-users.

- Collaborate with engineering leadership to establish architectural standards for AI integration, ensuring our systems remain modular, maintainable, and secure.

Required Skillset:

- Demonstrated expertise in building production-ready applications using Python, with a deep understanding of asynchronous programming and system architecture.

- Proven ability to design and implement Agentic AI workflows, leveraging frameworks like LangChain, LangGraph, and PyTorch to solve non-trivial machine learning problems.

- Strong grasp of modern AI paradigms, including RAG, vector databases, and deep learning, with a focus on practical application over theoretical exploration.

- Exceptional communication skills, with the ability to articulate complex technical trade-offs to non-technical stakeholders and influence product roadmaps.

- A collaborative mindset that thrives in hybrid work environments across Bangalore and Hyderabad, balancing independent problem-solving with active team participation.

- A strong academic foundation in Computer Science or a related quantitative field, paired with a relentless curiosity to stay updated on the rapidly evolving Generative AI landscape.