AI Engineer

Overview

Experience: 3–5 Years (Minimum 2 years dedicated AI experience)
Location: Bangalore (Hybrid)
Company: Circuit House Technologies
Role Overview
We’re looking for an AI Engineer to join the team behind TLDR, our flagship content discovery app. We are building the ultimate entry point for entertainment - helping users navigate the fragmented world of movies, shows, live sports, and music.
We aren't looking for a traditional backend dev; we need someone who lives and breathes the modern AI stack but has the engineering discipline to ensure those models actually work at scale.
Key Responsibilities

• End-to-End AI Engineering: Design, build, and optimize RAG systems for content discovery, focusing on retrieval accuracy and ranking for entertainment metadata.
• Model Implementation & Optimization: Work with SLMs and LLMs (Llama, Mistral, OpenAI, Gemini) for prompt engineering and model evaluation.
• Fine-Tuning: Perform supervised fine-tuning (SFT) or use techniques like LoRA/QLoRA to adapt models to our specific domain (e.g., understanding niche sports queries or music genres).
• Vector & Data Pipelines: Develop robust data pipelines for embeddings, sophisticated chunking strategies, and vector storage using tools like Pinecone, Milvus, or Qdrant.
• Orchestration & Agents: Use frameworks like LangChain, LlamaIndex, or DSPy to build agentic workflows that can "search" across multiple content providers.
• Evaluation Frameworks: Build and maintain systems to measure hallucination rates, grounding accuracy, and latency - ensuring our discovery results are factually correct.
• AI-Centric Backend: Own the "AI-as-a-service" layer. You’ll build the FastAPI/Python wrappers, handle asynchronous processing, and ensure your models are production-ready in Docker/Kubernetes.

Required Skills & Experience

• Core AI Engineering (3–5 Years Total): Minimum 2+ years of dedicated experience building and deploying AI applications in production.

Strong hands-on experience with:

• RAG architectures
• SLMs and LLMs
• Generative AI tools and model ecosystems
• Vector databases & embedding models
• AI frameworks: LangChain, LlamaIndex, HuggingFace, Haystack, DSPy, etc. Strong understanding of:
• Cloud technologies (AWS/GCP/Azure)
• Microservices architecture
• Databases
• RESTful APIs / GraphQL
• Docker & Kubernetes Experience deploying AI systems in production, with a focus on:
• Scalability
• Cost optimization
• Model performance tuning

Excellent problem-solving ability, architectural thinking, and data-driven **
**Preferred Qualifications

• Experience with SLMs (Small Language Models) and techniques like quantization or LoRA for running models efficiently.
• Familiarity with Agentic patterns.
• Knowledge of cloud-native AI services on AWS or GCP.
• A passion for sports, music, or digital media - helping users find "too long; didn't read" versions of what they love.