AI Platform Engineer

Team: Software Development

Location: Noida

Commitment: Full-time

Workplace Type: remote

Why Work for Us

• We are 100+ employees strong and growing. Our world-class team is supported by an industry-savvy board and an executive team of diverse background and experience across financial services and technology. 
• We offer competitive benefits that include Flexible PTO, Wellness benefits, Mobile/Internet subsidy, Employee Recognition Programs, and more!
• We are a remote-first company! We have regional hubs nationwide,  with presence in 4 Countries:  United States, Canada, India, and Singapore. 
• We embrace a culture that honors and celebrates diversity of backgrounds, approaches, and experiences.
• We are guided by our core values: Customer Delight, Make It Happen, Think Big, and We Over Me. Read more about our core values and how we live them every day on our website here.

How You’ll Make an Impact

• Design and build the core AI platform services that power advisor-facing features such as intelligent insights, meeting summaries, and next-step recommendations.
• Develop and maintain retrieval-augmented generation (RAG) and semantic search pipelines that allow our models to access and reason over financial data securely and efficiently.
• Integrate foundation models (OpenAI, Anthropic, AWS Bedrock, Azure OpenAI, or open-source alternatives) into scalable microservices and APIs.
• Create and manage prompt orchestration and versioning frameworks to support consistent and reliable AI responses across products.
• Develop evaluation, monitoring, and observability systems to ensure AI quality, compliance, and performance in production.
• Optimize inference performance, latency, and cost through model routing, caching, and fine-tuning strategies.
• Collaborate closely with product teams to enable new AI capabilities and ensure that AI outputs align with financial domain standards and regulations.
• Stay current with LLM and agentic technology advancements and help shape how Tandems applies them to real-world advisor workflows.

Ideal Person for this Role

• Core Engineering  Skills:
• 4+ years of software engineering experience with production systems
• Strong proficiency in Python and hands-on experience with LLM application frameworks (LangChain, LlamaIndex, Semantic Kernel, or DSPy)
• Proven experience building agent workflows and orchestrating multi-step AI processes
• Deep understanding of foundation model APIs (OpenAI, Anthropic, Google AI, AWS Bedrock, Azure OpenAI, or open-source models via Replicate/Hugging Face)
• Experience with prompt engineering, including techniques like few-shot learning, chain-of-thought, and prompt chaining
• Hands-on experience implementing RAG (Retrieval-Augmented Generation) systems with vector databases


• Agent Development Experience:
• Building autonomous and semi-autonomous agent systems that can plan, use tools, and execute multi-step tasks
• Implementing tool-calling and function-calling patterns with LLMs
• Creating agent memory systems (conversation history, long-term memory, knowledge bases)
• Orchestrating multi-agent systems or agent handoffs
• Experience with agent evaluation, debugging, and observability (using tools like LangSmith, Weights & Biases, or custom solutions)


• Foundation Model Integration:
• Managing different foundation models for specific tasks (routing between models based on complexity/cost/speed)
• Implementing streaming responses and real-time user interactions
• Handling context window management and conversation pruning strategies
• Building fallback and error recovery mechanisms for AI systems
• Cost optimization and rate limit management across multiple model providers

Perks and Benefits

• Tax-friendly Compensation
• Liberal Leave Policy
• Medical cover for the family, including parents
• Quarterly Wellness Benefit
• WFH Allowance
• Mobile/Internet subsidy (for smooth WFH experience)
• Employee Referral Program
• Employee Recognition Program
• And more!