AI Engineer at Goodera
Bengaluru, karnataka, India -
Full Time


Start Date

Immediate

Expiry Date

06 Sep, 26

Salary

0.0

Posted On

08 Jun, 26

Experience

2 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

No

Skills

Python, SQL, Generative AI, RAG Architecture, Agentic System Design, Model Optimization, FastAPI, Vector Databases, LangChain, LlamaIndex, Azure AI Studio, AWS Bedrock, Vertex AI, CI/CD, Transformer Architecture, Prompt Engineering

Industry

Software Development

Description
ABOUT GOODERA Goodera is the world’s leading employee volunteering platform, powering companies to scale employee volunteering experiences globally through our innovative technology platform and unique operating model. With a presence in over 100 countries and support for 30+ languages, we connect over 500 clients—including 60+ Fortune 500 companies—with meaningful volunteer opportunities tailored to their communities. To date, our impact has reached over 10 million beneficiaries, powered by 1 million+ employee volunteers and a network of 50,000+ nonprofit partners. Growing at 100% year on year, we are backed by top investors including Zoom Ventures, Elevation Capital, Nexus  Venture Partners, Omidyar Network, and Ursula Burns. THE ROLE The AI Engineer is a hybrid software engineer and AI specialist responsible for moving models out of the notebook and into production. The focus is on building "Systems around Models", designing the logic, data retrieval, and evaluation frameworks that make Generative AI reliable, scalable, and secure for end-users. KEY RESPONSIBILITIES * Agentic System Design: Build and maintain autonomous agents capable of tool-use, multi-step reasoning, and self-correction to solve complex workflows. * RAG Architecture: Develop and optimize Retrieval-Augmented Generation pipelines using hybrid search (keyword + semantic) and re-ranking to provide context-aware responses. * Model Optimization: Implement techniques like quantization, prompt caching, and fine-tuning (LoRA/QLoRA) to reduce latency and operational costs. * AI Quality Assurance: Design automated evaluation suites to measure "groundedness," hallucination rates, and toxicity using LLM-based metrics. * Integration & Deployment: Build robust APIs (FastAPI/GRPC) to serve AI features and manage model deployments within containerized environments. CORE REQUIREMENTS * Production Programming: Mastery of Python, with a focus on asynchronous patterns and type hinting. Proficiency in SQL and data modeling is required. * AI Fundamentals: Deep understanding of the Transformer architecture, tokenization, embedding spaces, and the mechanics of "Attention." * Data Strategy: Experience managing high-dimensional data within Vector Databases and performing ETL on unstructured data (PDFs, logs, web content). * Engineering Rigor: Familiarity with CI/CD for AI, including versioning prompts as code and tracking model experiments. TECHNICAL SPECIFICS * Frameworks: LangChain, LangGraph, LlamaIndex, or CrewAI for orchestration. * Inference & Serving: vLLM, Hugging Face TGI, or NVIDIA TensorRT-LLM. * Vector Infrastructure: Pinecone, Weaviate, Milvus, or pgvector. * Observability: LangSmith, Arize Phoenix, or Weights & Biases for tracing and debugging. * Platforms: Deep experience with Azure AI Studio, AWS Bedrock, or Vertex AI. * Models: Practical experience implementing both closed-source (GPT-4o, Claude 3.5) and open-source (Llama 3/4, Mistral) models.
Responsibilities
The AI Engineer is responsible for transitioning AI models from notebooks to production by building scalable systems around them. This includes designing autonomous agents, optimizing RAG pipelines, and implementing automated evaluation frameworks.
Loading...