About the Role :

Learning Pathways is building an AI-native enterprise SaaS platform that benchmarks organizational skills, identifies capability gaps, and generates personalized learning pathways using LLMs, RAG, and conversational AI.

We are looking for a hands-on Technical Lead to own the technical design and engineering execution of the platform. Reporting to the Founders, you will lead a cross-functional pod of 5 - 7 engineers, translating user stories into robust technical solutions and bridging the gap between applied AI and highly scalable enterprise infrastructure.

What You'll Build :

- Skills intelligence and benchmarking engines
- Learning Pathways and Learning Mentor conversational interfaces
- Atlas Companion multi-agent system
- High-throughput AI/RAG pipelines
- Enterprise APIs, secure multi-tenant architecture, and data service In Your First 90 Days, You Will :
- Audit our existing AI/RAG architecture and establish baselines for retrieval accuracy and inference latency.
- Standardize the CI/CD pipeline and deployment strategies for our core Python/FastAPI microservices.
- Architect and unblock the engineering team for the V1 launch of the Atlas Companion agent.
- Establish clear engineering cadences, code review standards, and technical documentation practices for your team.

Key Responsibilities :

1.

Technical Design and Architecture :

- Translate user stories and product requirements into scalable technical designs.
- Define application architecture, APIs, and service boundaries for both traditional backends and AI agent workflows.
- Design database schemas and data models across PostgreSQL, MongoDB, and vector stores.
- Make pragmatic architectural decisions regarding cloud infrastructure (AWS/GCP), GPU provisioning, and Kubernetes deployments.

2.



Hands-on Engineering and AI Integration :

- Write production-quality Python/FastAPI code for core backend services.
- Design and orchestrate multi-agent workflows using LangGraph and implement robust tool-calling using Model Context Protocol (MCP).
- Optimize model inference latency and throughput for conversational AI features using continuous batching frameworks like vLLM.
- Work with the Data Science team to translate AI/product concepts into scalable production systems.

3.

Scalability and Security :

- Establish appropriate caching (Redis/Valkey), asynchronous processing, and worker patterns.
- Manage GPU memory allocation and inference scaling to prevent system bottlenecks.
- Ensure secure multi-tenant architecture, data isolation, RLS, and strict authentication/authorization patterns.

4.

Engineering Leadership :

- Lead and mentor a growing engineering team of 5 to 7 backend and AI engineers.
- Break technical requirements into actionable engineering stories and support sprint estimations.
- Establish modern engineering practices around testing, CI/CD, MLFlow, and observability (LangSmith/Datadog).

Requirements :

1.

Core Systems and Architecture :

- Backend : Deep expertise in Python and FastAPI.
- Databases : PostgreSQL, MongoDB, Redis/Valkey, and advanced database/query optimization.
- Infrastructure : Distributed systems, Docker, Kubernetes, and cloud-native development (AWS/GCP).
- Security :



Strong grasp of AuthN/AuthZ, Row-Level Security, and enterprise data isolation.

2.

Applied AI and ML Engineering :

- LLM Orchestration : Experience building production applications with LangChain, LangGraph, and LangSmith.
- Information Retrieval : Advanced RAG patterns, semantic/hybrid search, embedding models, and re-ranking architectures.
- Agentic Systems : Designing robust agent/tool architectures (MCP : Client and Server).
- Ecosystem : Familiarity with HuggingFace and the Transformers library.

3. Bonus / Nice-to-Haves :

- Node.js / TypeScript : Ability to navigate and contribute to existing Node.js services or front-end BFFs.
- Model Optimization : Experience with Supervised Fine-Tuning, specifically Parameter-Efficient Fine-Tuning (PEFT) like LoRA.
- High-Throughput Serving : Experience deploying and scaling open-weight models using vLLM.

What We're Looking For :

- 7+ years of software engineering experience, with significant time as a Technical Lead or Software Architect.
- Experience building production SaaS or enterprise platforms, specifically integrating AI/LLM components.
- Ability to move fluidly from user story - architecture - database - API - production.
- Thinks about scalability and security from the beginning, while knowing when to build for scale vs. keep things simple.
- Takes ownership of the technical outcome rather than just completing assigned tasks.

Compensation, Benefits and Culture :

- Work Setup : In office in Hyderabad
- Benefits : Competitive pay, learning support

Equal Opportunity Statement :

Learning Pathways is an equal-opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees.

📌 Technical Lead - AI Platform & System (India)
🏢 Learning Pathways
📍 India