Description

Key Responsibilities

- Architect, build, and deploy agentic AI systems using frameworks such as LangGraph, Google ADK,Autogen, Semantic Kernel, CrewAI, and LangChain.
- Design and implement RAG pipelines leveraging vector databases (OpenSearch, Pinecone, FAISS, or Weaviate).
- Develop modular and reusable AI agent architectures for dynamic reasoning and tool orchestration.
- Integrate and fine-tune foundation models (GPT, Claude, Gemini, Mistral, Llama, etc.) for domain-specific tasks.
- Work with APIs, embeddings, and context optimization for large-scale AI workflows.
- Collaborate with platform, data, and product teams to ensure robust integration and deployment.
- Implement observability, performance tracking, and continuous evaluation of model and agent behavior.
- Stay up to date with the latest research and open-source developments in LLMs, agents, and cognitive frameworks.
- Mentor and guide junior engineers on prompt design, agent architecture, and optimization techniques.

Required Skills & Experience

- 5–10 years of total experience in AI / ML engineering, including at least 2 years in Generative AI.
- Proven expertise with agentic frameworks — LangGraph, Google ADK, Semantic Kernel, CrewAI, LangChain, or similar.
- Strong programming skills in Python and familiarity with microservice or API-based systems.
- Hands-on experience with LLMs, vector search, and retrieval-augmented generation ( ) architectures.
- Good understanding of prompt engineering, model evaluation, and context optimization.
- Experience with cloud platforms (AWS, Azure, or GCP) and containerized deployments.
- Exposure to model fine-tuning, LoRA, or custom embedding generation.
- Build multimodal content generation workflows:

Text → Image (Stable Diffusion, Runway, Sora, GPT,



Midjourney APIs)Image → Image / Video (image transformation, video synthesis)Text → Video (Veo, Sora, Pika Labs, Runway ML, or similar)Text → Audio / Speech (TTS systems, diffusion-based audio models)

Positive to Have

- Knowledge of multimodal AI (text, image, audio, video).
- Experience building or contributing to internal agent SDKs and AI developer platforms.
- Understanding of tool-augmented reasoning, graph-based agent workflows, and memory architectures.
- Familiarity with data governance, hallucination control, and AI safety best practices.
- Experience optimizing inference latency and cost for production-scale models.

Soft Skills

- Strong problem-solving and analytical thinking abilities.
- Excellent communication and cross-functional collaboration skills.
- Self-driven, with a focus on ownership and innovation.
- Ability to translate complex technical ideas into practical, scalable implementations.

Why Join Us

- Work at the forefront of agentic and generative AI innovation.
- Collaborate with a highly skilled AI research and engineering team.
- Shape the architecture of next-generation intelligent systems.
- Opportunity to lead high-impact projects with cutting-edge LLM and reasoning frameworks.
- Competitive compensation, flexible work setup, and a culture centered on innovation and technical excellence.

About BRAHMA AI:
BRAHMA AI is the next generation of enterprise media technology formed through the integration of Prime Focus Technologies and Metaphysic. By combining CLEAR®, CLEAR® AI, ATMAN, and VAANI into one ecosystem, BRAHMA AI enables enterprises to manage, create, and distribute content with intelligence, security, and efficiency.

Proven, scalable, and enterprise-tested, BRAHMA AI is helping global organizations accelerate growth, efficiency, and creative impact in the AI-powered era.

📌 Senior / Principal Generative AI Engineer (Bengaluru)
🏢 Brahma
📍 Bengaluru