AI/ML Developer

keka

Mohali 3 Years Exp Posted 52d ago

Key Responsibilities

Design and develop scalable Generative AI applications across use cases such as text generation, summarization, search, and automation.
Architect and implement LLM-powered systems, including RAG (Retrieval-Augmented Generation), agent-based workflows, and multi-step reasoning pipelines.
Build and integrate AI workflows using frameworks such as LangChain, LlamaIndex, and workflow orchestration tools like n8n.
Develop and optimize backend services using Python (FastAPI/Flask) to expose AI capabilities via APIs.
Design and manage vector-based retrieval systems using tools such as Pinecone, Weaviate, FAISS, or Chroma.
Integrate with leading AI platforms such as OpenAI, Anthropic, and Hugging Face, ensuring optimal performance, cost, and latency.
Build robust data pipelines for ingestion, preprocessing, chunking, and embedding of structured and unstructured data.
Take ownership of transitioning AI solutions from POC to production, ensuring scalability, reliability, and maintainability.
Implement monitoring, logging, and evaluation mechanisms to track model performance, accuracy, and system health.
Collaborate with cross-functional teams (product, design, data) to translate business requirements into AI-driven solutions.
Document system architecture, workflows, and technical decisions clearly for long-term maintainability.

Required Skills & Competencies

Bachelor’s degree in Computer Science, Engineering, or a related technical field.
3-5 years of experience in software development with strong exposure to Generative AI or machine learning systems.
Strong proficiency in Python with experience in building production-grade applications.
Hands-on experience with Generative AI frameworks such as LangChain, LlamaIndex, or similar.
Solid understanding of LLMs, prompt engineering, and RAG architectures.
Experience building and consuming REST APIs.
Familiarity with vector databases and semantic search systems.
Experience working with Git and modern development workflows.

Preferred Skills

Experience with cloud platforms (AWS, Azure, or GCP) for deploying AI/ML solutions.
Exposure to n8n or similar workflow automation tools for orchestrating AI pipelines.
Understanding of LLM optimization techniques including token management, caching, and cost control.
Experience with fine-tuning, embeddings, or open-source LLMs is a plus.
Knowledge of MLOps / LLMOps practices including CI/CD, monitoring, and evaluation frameworks.
Awareness of AI security concerns such as prompt injection, data privacy, and output validation.
Strong problem-solving, communication, and collaboration skills.
- Self-driven mindset with the ability to work in a fast-paced, evolving AI landscape.