Artificial Intelligence Engineer

AI Engineer

About the job Location: Hyderabad, India (WFH, 2-3 times a month in office) Type: Full Time/ Senior Individual Contributor (Hands On) Salary: Negotiable based on experience Experience: 6+ years overall with 2+ years in AI/GenAI Dev Hours: 3PM-12MN (Semi-Flexible)

About Us Bonterra exists to propel every doer of good to their peak impact. We measure that impact against our vision to increase the giving rate as a percentage of GDP from 2% to 3% by 2033. We know that this goal is lofty, but we are confident that the right technology and expertise will strengthen trust in the sector, allowing the social good industry to accelerate growth and reach peak impact. Bonterra's differentiated, end-to-end solutions collectively support a unique network of over 20,000 customers, including over 16,000 nonprofit organizations and over 50 percent of Fortune 100 companies. Learn more at bonterratech.com.

About The Role We're hiring a senior, hands-on engineer to architect and build production-grade AI agents and intelligent applications. This is not a strategy or oversight role — you will be writing code, designing systems, setting architectural and operational standards, and shipping AI features end-to-end. You'll work across the stack: backend services, agent orchestration, LLM integration, and cloud infrastructure. We're looking for an AI-forward engineer — someone who actively explores new AI capabilities, has strong opinions on what works in production, and treats AI as a first-class engineering discipline rather than a bolted-on feature.

What You'll Do

• Design and build production AI agents that automate workflows, handle complex multi-step tasks, and integrate with internal and external systems
• Architect end-to-end AI solutions including agent orchestration, tool use, RAG pipelines, memory/state management, and evaluation frameworks
• Develop scalable backend services in Python (and Node.js where applicable) to support AI workloads
• Build and optimize RAG systems including chunking strategies, embedding pipelines, vector search, and retrieval evaluation
• Integrate LLMs (Claude, GPT, Gemini, open-source models) into production systems with appropriate guardrails, observability, and cost controls
• Deploy and operate AI systems on AWS with attention to latency, scale, reliability, and security
• Establish engineering practices for AI development: prompt versioning, eval pipelines, A/B testing, monitoring, and incident response
• Collaborate with product and business stakeholders to translate ambiguous problems into shippable AI solutions
• Stay current with the rapidly evolving AI ecosystem and bring credible recommendations on tooling, models, and architectural patterns

Governance, Standards & Operations

• Define and uphold architectural standards for AI systems — including agent design patterns, orchestration approaches, prompt management, model selection, and integration patterns Establish AI governance practices including guardrails, safety controls, responsible AI principles, audit trails, and access controls for sensitive data and model usage
• Ensure compliance with relevant data privacy, security, and regulatory requirements applicable to AI workloads (e.g., handling of PII, data residency, model usage policies)
• Own production operations for AI systems — including monitoring, alerting, incident response, and on-call practices for AI-specific failure modes (hallucinations, drift, latency degradation, cost spikes)
• Drive cost and performance optimization across the AI stack — including model selection trade-offs, caching strategies, token usage management, infrastructure right-sizing, and workload routing
• Build observability into AI systems by default — tracing, logging, evaluation pipelines, and dashboards that make AI behavior in production visible and debuggable

Must-Have Qualifications

• 6+ years of professional software engineering experience
• Strong hands-on Python for backend development and AI workloads
• Hands-on experience building AI agents in production — not just LLM API integration, but agent orchestration, tool use, and multi-step reasoning
• Proficiency with AI frameworks such as LangChain, LangGraph, LlamaIndex, or equivalent
• Hands-on AWS experience including core services such as Lambda, API Gateway, RDS, DynamoDB, S3, and IAM
• Hands-on RAG experience including vector databases (Pinecone, Weaviate, FAISS, Chroma, etc.), embeddings, and retrieval optimization
• Experience with non-relational databases (DynamoDB, MongoDB, Redis, vector stores, or similar)
• Experience operating production systems — including monitoring, alerting, incident response, and performance/cost optimization
• Solid understanding of REST APIs, microservices, async processing, and event-driven architectures
• Ability to design systems, not just implement specs — strong architectural judgment and communication

Nice-to-Have

• Node.js experience for service development and integrations
• Hands-on experience with AWS Bedrock or other managed AI/ML services
• Experience with multiple LLM providers and model evaluation
• Prompt engineering depth and experience with evaluation frameworks (RAGAS, custom eval harnesses, etc.)
• Basic understanding of Evidently and Langfuse for AI/ML observability and monitoring
• MLOps / LLMOps experience including model deployment, monitoring, and CI/CD for AI systems
• Experience with infrastructure-as-code (Terraform, CDK)
• Familiarity with AI governance, responsible AI practices, and compliance frameworks (GDPR, SOC 2, HIPAA, or industry-specific equivalents)
• Frontend familiarity (React, Next.js) for building AI-powered user interfaces
• Relevant AWS or AI certifications What We're Looking For (Attributes)
• Builder mindset: You ship. You prototype quickly, iterate based on real feedback, and have a track record of taking AI projects from idea to production.
• AI-forward thinking: You stay current, experiment with new models and tools, and have informed opinions about what works.
• Pragmatic architect: You make sound build-vs-buy decisions, understand tradeoffs, and design for the actual problem — not the most impressive solution.
• Strong communicator: You explain technical decisions clearly to engineers and non-engineers alike.
• Honest about limits: You know where AI shines and where it fails, and you don't oversell. At Bonterra, we’re building AI-powered tools to solve real human challenges—and we want teammates who share that enthusiasm. We value people who will champion AI and bring diverse perspectives from different industries, backgrounds, and cultures. Together, we create AI that breaks down barriers, empowers communities, and delivers better outcomes. At this time, we are unable to consider candidates who require current or future sponsorship for employment authorization. ____________________________________________________________________________________

Our Culture At Bonterra, we’re innovating with a higher purpose: to increase giving to 3% of US GDP by 2033, creating $573 billion more in global impact every year. At Bonterra, we foster an inclusive, equitable culture where every team member belongs and contributes to meaningful impact. Read more about our values and culture here ____________________________________________________________________________________

Equal Opportunity & Accommodations At Bonterra, we are proud to be an Equal Opportunity Employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. We provide equal employment opportunities without regard to race, color, religion, sex (including pregnancy, sexual orientation, or gender identity), national origin, age, disability, veteran status, or any other characteristic protected by law. If you require a reasonable accommodation during the application process, please submit here