Job Number: 202503001
Location Pune, IN
Role Type: Individual Contributor
Role: Software Engineer – GenAI
Date Posted: March 7, 2025
Experience: 3-5 Years
Employment Type: Full-Time
Technologies: GenAI, Python

At ZasmLabs, we believe in providing our engineers with real-world challenges to apply the technical knowledge they have gained working relentlessly for years. Our mission is to enable businesses to grow by leveraging strategic IT implementation and keep up with the ever-changing dynamics of the industry. As a Software Engineer – GenAI, you will be part of a dynamic team, working on exciting challenges that will help business leverage the edge of AI.

Responsibilities

Responsibilities

• Develop and implement generative AI agents using frameworks like LangChain or Llama-Index.
• Apply prompt engineering techniques to design effective queries and ensure optimal LLM responses for diverse use cases.
• Master advanced LLM functionalities, including prompt optimization, hyperparameter tuning, and response caching.
• Implement Retrieval-Augmented Generation (RAG) workflows by integrating vector databases like Pinecone, Weaviate, Supabase, or PGVector for efficient similarity searches.
• Work with embeddings and build solutions that leverage similarity search for personalized query resolution.
• Explore and process multimodal data, including image and video understanding and generation.
• Integrate observability tools for monitoring and evaluating LLM performance to ensure system reliability.
• Build and maintain scalable backend systems using Python frameworks such as FastAPI, Django, or Flask.
• Design and implement RESTful APIs for seamless communication between systems and services.
• Optimize database performance with relational databases (PostgreSQL, MySQL) and integrate vector databases (Pinecone, PGVector, Weaviate, Supabase) for advanced AI workflows.
• Implement asynchronous programming and adhere to clean code principles for maintainable, high-quality code.
• Seamlessly integrate third-party SDKs and APIs, ensuring robust interoperability with external systems.
• Develop backend pipelines for handling multimodal data processing, supporting text, image, and video workflows.
• Manage and schedule background tasks with tools like Celery, cron jobs, or equivalent job queuing systems.
• Leverage containerization tools such as Docker for efficient and reproducible deployments.

Requirements

• Strong Programming Skills: Proficiency in Python and experience with backend frameworks like FastAPI, Django, or Flask.
• Generative AI Expertise: Knowledge of frameworks like LangChain, Llama-Index, or similar tools, with experience in prompt engineering and Retrieval-Augmented Generation (RAG).
• Data Management: Hands-on experience with relational databases (PostgreSQL, MySQL) and vector databases (Pinecone, Weaviate, Supabase, PGVector) for embeddings and similarity search.
• Machine Learning Knowledge: Familiarity with LLMs, embeddings, and multimodal AI applications involving text, images, and video, along with a strong understanding of NLP and core machine learning concepts.
• Deployment Experience: Proficiency in deploying AI models in production environments using Docker and managing pipelines for scalability and reliability.
• Testing and Debugging: Strong skills in writing and managing unit and integration tests (e.g., Pytest), along with application debugging and performance optimization.
• Asynchronous Programming: Understanding of asynchronous programming concepts for handling concurrent tasks efficiently.

Qualifications

• BS/MS in Computer Science, or equivalent in related technical experience
• 3-5 years of experience developing commercial software
• 1+ years of experience with GenAI, Prompt Writing is a must
• Fluency in English language (verbal and written) is a must.