BENGALURU · FULLTIME
SDE III - Agentic AI
Arintra
Bengaluru · onsite · Posted 11d ago
Your match
Sign in to see your match score, skill gaps & tailored resume.
Section · 01
About this role
Responsibilities:
- Build and own production-grade backend services handling real user traffic.
- Design and build LLM agents involving LLMs, tool calling, and multi-step workflows.
- Own agents end-to-end from architecture and prompts to tools, evaluation, deployment, and post-production improvements.
- Design agent architecture covering tool orchestration, context/memory, guardrails, and decision-making on when to use an agent vs. traditional code.
- Build and maintain evaluation frameworks to measure agent quality and reliability.
- Work with golden datasets, regression suites, LLM-as-judge, human review, trajectory evaluations, and other evaluation approaches.
- Implement eval-gated releases, CI checks, shadow/canary deployments, and rollback mechanisms.
- Monitor production agents through tracing, drift monitoring, retries, timeouts, latency, and cost controls.
- Optimize model selection based on accuracy, cost, and latency, including experience migrating between models.
- Contribute to engineering excellence, architecture decisions, code quality, prioritization, and mentorship.
- Take ownership of production issues and drive fixes after launch.
Requirements:
- 6+ years of experience, primarily owning production backend services with real traffic.
- Strong backend engineering experience; language/technology stack is flexible.
- At least 1+ year of hands-on experience building LLM agents in production with real users.
- Experience with LLM + tool calling + multi-step agent workflows.
- Must have owned at least one agent end-to-end: design, prompts, tools, evaluations, deployment, and post-launch fixes.
Sourced from instahyre
Let the agent run this one for you.
Tailored resume, auto-apply, and referral lookup — in under 2 minutes.
Section · 02
Skills
Section · Company
About Arintra
Arintra
11-50
employees
2020
6 years old
Austin
US
About
US hospitals and clinics are losing $125B every year due to delayed and inaccurate medical coding. Arintra is solving this problem by automating medical coding using AI and clinical NLP. Arintra converts a patient chart instantly into insurance claims with 96% accurate medical codes and zero human intervention.
Arintra solution is specifically tailored to cater to the varying requirements of ambulatory and outpatient specialties, emergency department services, and inpatient settings, ensuring comprehensive coverage across all healthcare domains.
Arintra’s software leverages proprietary artificial intelligence and natural language processing algorithms to process patient charts directly from the EHR to create a direct-to-billing claim. Arintra autonomously goes through every stage of the claim submission process and ensures a clean claim for optimal reimbursements without any human intervention. Arintra is integrated with all the top EHRs to ensure effortless implementation without any change in the workflow.
Arintra’s medical coding software offers two powerful modes for medical coding: autonomous coding mode and assisted coding mode. In autonomous coding mode, direct-to-billing claims are generated autonomously with high accuracy, streamlining the billing process for healthcare provider organizations. Whereas, assisted coding mode allows medical coders to meticulously review and optimize charges before submission, leading to increased efficiency and precision in the coding process. With Arintra, healthcare provider organizations can rely on precise direct-to-billing claims that include essential codes like E/M levels, CPT, ICD-10, HCC, HCPCS with appropriate modifiers and units.
Arintra’s coding solution provides extensive coverage and flexibility, catering to various coding domains such as professional coding, professional-fee coding, facility coding, and inpatient coding.
Industries
Employee ratings
7 reviews
Culture
2.0
Career growth
2.0
Work-life
1.6
Find them on