Technical Architect

Bacancy Technology; United States; Remote; USD 190,000 - 240,000; Full time

Job summary

Bacancy Technology is seeking a Technical Architect to lead production-grade AI and agentic systems for healthcare and fintech. You will own end-to-end architecture for internal platforms and guide engineering teams, with hands-on PoCs, code reviews, and technical leadership without direct reports.

Responsibilities include defining target-state architectures, building scalable distributed systems, and ensuring security, privacy, and regulatory alignment while collaborating with clients and

Qualifications

• 10+ years in software engineering and architecture.
• 8+ years hands-on core development.
• Backend: two or more of Node.js, .NET, Java, Python; REST/GraphQL APIs, async processing.
• Frontend: React/Angular/Vue with component architecture and state management.
• Database: PostgreSQL with advanced design, indexing, and replication; NoSQL & caching familiarity.
• 3+ years delivering AI/ML solutions, incl. LLMs.
• Production experience with agentic frameworks and multi-agent orchestration.
• Strong system design for distributed systems, microservices, event-driven, scalable and observable.
• Knowledge of RAG, embeddings, vector databases, prompt engineering, and LLM evaluation.
• Experience with containers, Kubernetes, CI/CD and IR as code on a major cloud.
• Healthcare or fintech domain experience; HIPAA/SOC2 awareness is a plus.
• Bachelor's degree in CS/Engineering or equivalent experience.

Responsibilities

• Define target-state architecture for AI-enabled platforms and migrations.
• Design scalable distributed systems with microservices and data pipelines.
• Document build-vs-buy decisions and architectural trade-offs.
• Ensure cloud-agnostic designs across AWS, Azure, and GCP.
• Architect agentic workflows and multi-agent systems with tool use, memory and state management.
• Design RAG pipelines over structured/unstructured data and guardrails for AI agents.
• Set up observability, cost/latency monitoring for LLM-based systems.
• Lead technical discovery workshops and translate business needs into technical roadmaps.
• Review code and designs to enforce quality, security, and performance.
• Mentor engineers and raise AI engineering capability.

Skills

System design

Technical leadership

Architecture decisions

Client workshops

Security & privacy design

Education

Bachelor's in CS/Engineering

Tools

Node.js

.NET/C#

Java (Spring Boot)

Python (FastAPI/Django/Flask)

React/Angular/Vue

PostgreSQL

pgvector

MongoDB

Redis

Docker

Kubernetes

CI/CD

Job description

Role summary

We are hiring a Technical Architect to design and lead production-grade AI and agentic systems for regulated industries, with a primary focus on healthcare and a secondary focus on fintech. You will own end-to-end architecture for our internal platforms and act as the senior technical voice in client engagements. The role is moderately hands-on: you will build proofs of concept, review code, and guide engineering teams, without direct reports.

Items in square brackets are placeholders to fill in before posting.

Key responsibilities

Architecture and system design

• Define target-state architecture for AI-enabled platforms, including current-state assessment, target state and migration plan.
• Design scalable, resilient distributed systems: microservices, event-driven patterns, APIs, data pipelines and caching.
• Make and document build-vs-buy, technology and trade-off decisions through architecture decision records.
• Keep designs cloud-agnostic and portable across AWS, Azure and GCP.

AI and agentic systems

• Architect agentic workflows and multi-agent systems, including orchestration, tool use, memory and state management.
• Design retrieval-augmented generation (RAG) pipelines over structured and unstructured data.
• Build guardrails into every agent: scope limits, output validation, hallucination checks, fallback paths and human-in-the-loop review for high-risk actions.
• Set up evaluation, observability and cost/latency monitoring for LLM-based systems in production.
• Select and evaluate LLMs, agentic frameworks and vector stores against business and compliance needs.

Security, privacy and compliance

• Embed privacy-by-design into data flows: data minimization in prompts and agent payloads, encryption, access control and audit trails.
• Partner with Security, Compliance and Legal to meet regulatory requirements in healthcare and financial services.
• Contribute to compliance documentation and audits.

Client and stakeholder engagement

• Lead technical discovery and solution workshops with clients.
• Translate business and regulatory needs into technical designs, estimates and delivery roadmaps.
• Present architecture and trade-offs clearly to executives and engineers alike.
• Support pre-sales with solution proposals and technical responses.

Technical leadership

• Build proofs of concept to validate architecture choices before full delivery.
• Review code and designs to enforce standards for quality, security and performance.
• Mentor engineers and tech leads; raise the team's AI engineering capability.

Required qualifications

• 10+ years of overall experience in software engineering and architecture.
• 8+ years of hands-on core development, with deep expertise in the technologies below.
• Backend: Strong experience in at least two of Node.js, .NET (C#), Java (Spring Boot) and Python (FastAPI, Django or Flask). Able to design RESTful and GraphQL APIs, async processing and service-to-service communication.
• Frontend: Working experience with React, Angular or Vue, including component architecture, state management, performance and secure handling of sensitive data in the browser. Able to guide frontend teams on architecture and best practices.
• Database: Strong PostgreSQL experience, including schema design, indexing, query tuning, partitioning, replication and backup/recovery. Experience using pgvector or similar for AI workloads is a plus, as is familiarity with NoSQL and caching (e.g., MongoDB, Redis).
• 3+ years designing and delivering AI/ML solutions, including LLM-based applications and AI architecture.
• Production experience with at least one agentic framework, including multi-agent orchestration, tool/function calling and agent memory. Systems must have run in production with real users, not only prototypes.
• Strong system design skills: distributed systems, microservices, event-driven architecture, API design, scalability, fault tolerance and observability.
• Working knowledge of RAG, embeddings and vector databases, prompt engineering and LLM evaluation methods.
• Experience with containers, Kubernetes, CI/CD and infrastructure as code on at least one major cloud.
• Professional experience in the healthcare or fintech domain (see Domain expertise).
• Bachelor's degree in Computer Science, Engineering or a related field, or equivalent experience.

Domain expertise

Candidates must have worked in healthcare or fintech. Healthcare experience is preferred; fintech candidates with strong regulated-domain experience are welcome.

Healthcare (preferred)

• Designing HIPAA-compliant architectures, including PHI handling, de-identification, consent and audit logging.
• Interoperability standards such as FHIR (R4), HL7 v2 and CDA, and integration with EHR/EMR systems.
• Healthcare authentication patterns such as SMART on FHIR, OAuth 2.0 and SAML.
• Familiarity with clinical, payer or provider workflows (claims, prior authorization, care management, clinical documentation).
• Awareness of frameworks such as HITRUST and SOC 2, and of regulations on AI in clinical settings.

Fintech

• Designing PCI DSS-compliant systems, including scope reduction, tokenization and encryption of sensitive data.
• Knowledge of the payments or lending lifecycle: authorization, settlement, reconciliation, disputes and idempotency.
• Guardrails for AI agents that touch money movement, such as deterministic handoffs and human approval for financial actions.
• Awareness of KYC/AML, GDPR, SOC 2, model risk management and AI regulations such as the EU AI Act.

Preferred qualifications and soft skills

Nice to have

• Experience with agent interoperability standards such as Model Context Protocol (MCP) or agent-to-agent protocols.
• MLOps/LLMOps experience: model deployment, versioning, monitoring and prompt management.
• Experience with responsible AI practices: bias testing, explainability and AI governance frameworks.
• Cloud architecture certification (AWS, Azure or GCP).
• Experience in consulting or client-facing delivery, including estimation and fixed-scope engagements.

Soft skills

• Clear written and verbal communication, from executive summaries to detailed technical specs.
• Sound judgment in high-stakes, cross-functional discussions with Security, Compliance and Legal.
• Comfort with ambiguity and the ability to turn vague requirements into concrete designs.
• A mentoring mindset and the ability to lead through influence rather than authority.